Machine learning driven high-throughput screening of S and N-coordinated SACs for eNRR

This study constructs 196 transition metals (TM)@S_<i>x</i>N_<i>y</i> single-atom catalysts (SACs) (<i>x</i> = 0–4 and <i>y</i> = 0–4) and employs the eXtreme Gradient Boosting (XGBoost) classification model in machine learning (ML) for effectively distinguishing qualified and unqualified catalysts. The prediction accuracy rate is high, up to 95%. The SHapley Additive exPlanations (SHAP) analysis reveals that the N≡N bond length and the number of outermost d electrons (<i>N</i>_d) can well describe the nitrogen (N₂) reduction reaction (NRR) activity. The relationships between N≡N, <i>N</i>_d, the adsorption energies of different intermediates (<inline-formula id="M1"> <math id="mathml_M1" display="inline" overflow="scroll"><mrow class="MJX-TeXAtom-ORD"><mi mathvariant="normal">Δ</mi></mrow><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mi>E</mi></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mo>∗</mo></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mtext>N</mtext></mrow><mrow class="MJX-TeXAtom-ORD"><mn>2</mn></mrow></msub></mrow></msub></mrow></msub></math></inline-formula>, <inline-formula id="M2"> <math id="mathml_M2" display="inline" overflow="scroll"><mrow class="MJX-TeXAtom-ORD"><mi mathvariant="normal">Δ</mi></mrow><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mi>E</mi></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mo>∗</mo></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mtext>N</mtext></mrow><mrow class="MJX-TeXAtom-ORD"><mn>2</mn></mrow></msub><mtext>H</mtext></mrow></msub></mrow></msub></math></inline-formula>, and <inline-formula id="M3"> <math id="mathml_M3" display="inline" overflow="scroll"><mrow class="MJX-TeXAtom-ORD"><mi mathvariant="normal">Δ</mi></mrow><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mi>E</mi></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mo>∗</mo></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mtext>N</mtext><mtext>H</mtext></mrow><mrow class="MJX-TeXAtom-ORD"><mn>2</mn></mrow></msub></mrow></msub></mrow></msub></math></inline-formula>), the general descriptor (<i>φ</i>), and the Gibbs free energy of key steps (<inline-formula id="M4"> <math id="mathml_M4" display="inline" overflow="scroll"><mrow class="MJX-TeXAtom-ORD"><mi mathvariant="normal">Δ</mi></mrow><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mi>G</mi></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mo>∗</mo></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mtext>N</mtext></mrow><mrow class="MJX-TeXAtom-ORD"><mn>2</mn></mrow></msub></mrow></msub></mrow></msub></math></inline-formula>, <inline-formula id="M5"> <math id="mathml_M5" display="inline" overflow="scroll"><mrow class="MJX-TeXAtom-ORD"><mi mathvariant="normal">Δ</mi></mrow><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mi>G</mi></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mo>∗</mo></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mtext>N</mtext></mrow><mrow class="MJX-TeXAtom-ORD"><mn>2</mn></mrow></msub><mo>−</mo></mrow></msub><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mo>∗</mo></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mtext>N</mtext></mrow><mrow class="MJX-TeXAtom-ORD"><mn>2</mn></mrow></msub><mtext>H</mtext></mrow></msub></mrow></msub></math></inline-formula>, and <inline-formula id="M6"> <math id="mathml_M6" display="inline" overflow="scroll"><mrow class="MJX-TeXAtom-ORD"><mi mathvariant="normal">Δ</mi></mrow><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mi>G</mi></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mo>∗</mo></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mtext>N</mtext><mtext>H</mtext></mrow><mrow class="MJX-TeXAtom-ORD"><mn>2</mn></mrow></msub><mo>−</mo></mrow></msub><msub><mrow class="MJX-TeXAtom-ORD"><mrow class="MJX-TeXAtom-ORD"><mo>∗</mo></mrow></mrow><mrow class="MJX-TeXAtom-ORD"><msub><mrow class="MJX-TeXAtom-ORD"><mtext>N</mtext><mtext>H</mtext></mrow><mrow class="MJX-TeXAtom-ORD"><mn>3</mn></mrow></msub></mrow></msub></mrow></msub></math></inline-formula>) indicate that moderate nitrogen activation can enhance the reaction activity. Among the 17 screened SACs, Mo@S₃N₁, and W@S₃N₁ demonstrate the best catalytic performance, with limiting potential (<i>U</i>_L) values of only −0.26 and −0.25 V under implicit solvation conditions. The electronic properties and variations in N≡N and TM–N bond lengths are investigated to reveal the origin of NRR activity. This study provides the decisive features and NRR dataset for ML research, as well as a feasible strategy for rational design of NRR SACs.